© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 241808
    Prev
    Next
    INDEX
    Explanations

    invitation letter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bok
    0.44
     ROYAL
    0.43
    foreach
    0.42
    Royal
    0.42
    dött
    0.42
    rk
    0.41
    Berlin
    0.40
    t
    0.40
    Corona
    0.40
    mostrar
    0.40
    POSITIVE LOGITS
    শিক্ষা
    0.48
     nuevamente
    0.48
     trụ
    0.46
     таксама
    0.46
    နိုင်သည်။
    0.46
     übernahm
    0.46
    に加え
    0.46
     также
    0.45
     แก้
    0.45
     prudence
    0.44
    Activations Density 0.000%

    No Known Activations